Research map / Label-efficient and robust learning / Self-supervised and contrastive
MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging
Shufeng Kong, Zijie Wang, Nuan Cui, Hao Tang, Yihan Meng, Yuanyuan Wei, Feifan Chen, Yingheng Wang, Zhuo Cai, Yaonan Wang, Yulong Zhang, Yuzheng Li and 3 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add clinical knowledge constraints (ablation) | MIRNet · TongueAtlas-4K test | Macro-F1: -4.4% when removed | Improved |
| add clinical knowledge constraints (ablation) | MIRNet · TongueAtlas-4K test | Example-F1 and Micro-F1: -3.2% when removed | Improved |
| replace MLP classifier with GAT label-graph decoder (ablation) | MIRNet · TongueAtlas-4K test | Macro-F1: -3.2% when removed | Improved |
| replace MLP classifier with GAT label-graph decoder (ablation) | MIRNet · TongueAtlas-4K test | Macro Recall: -8.1% when removed | Improved |
| add MAE self-supervised pretraining (ablation) | MIRNet · TongueAtlas-4K test | Macro-F1: -23.0% when removed | Improved |
| add MAE self-supervised pretraining (ablation) | MIRNet · TongueAtlas-4K test | Macro Recall: -29.0% when removed | Improved |
| add boosting ensemble on weakest labels | MIRNet · TongueAtlas-4K test | Macro-F1: 0.525425 -> 0.537061 | Improved |
| add boosting ensemble on weakest labels | MIRNet · TongueAtlas-4K test | Macro Recall: 0.599019 -> 0.655388 | Improved |
| add boosting ensemble on weakest labels | MIRNet · TongueAtlas-4K test | Example-F1: 0.680389 -> 0.674805 | Hurt |
| add boosting ensemble on weakest labels | MIRNet · TongueAtlas-4K test | Macro Precision: 0.507837 -> 0.499404 | Hurt |
Closest papers by meaning
- M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding (ICLR 2026 · similarity 0.85)
- GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis (NeurIPS 2026 · similarity 0.85)
- MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision (AAAI 2026 · similarity 0.85)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.84)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.84)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
